Multi-element universal model platform modeling method, electronic equipment and computer readable storage medium

Abstract

The invention discloses a multi-element universal model platform modeling method. The method comprises the following steps of: establishing a data processing universal process, accessing a data universal format, and establishing a sample library and a feature library for pre-stored user information according to the data processing universal process and the data universal format; establishing a model algorithm library for processing multi-element scene businesses, and providing the model algorithm library to a preset configuration file for calling; and receiving a modeling instruction of a specific scene business, calling a model algorithm corresponding to the specific scene business from the model algorithm library through the configuration file, and carrying out modeling through the modelalgorithm corresponding to the specific scene business according to user information, according with the specific scene business, in the sample library and the feature library. According to the method, modeling can be rapidly carried out by utilizing a multi-element universal model, so that accumulation of resource parameters and model parameters is realized and periodical analysis results are output.

Description

technical field [0001] The invention relates to the field of computer information technology, in particular to a multivariate general model platform modeling method, electronic equipment and a computer-readable storage medium. Background technique [0002] At present, there is no general solution for business forecasting in each scenario. In addition, the high cost of Spark big data learning leads to slow access to modeling tasks for new projects or new businesses and low code reuse rate. Therefore, the design of the modeling method in the prior art is not reasonable enough and urgently needs to be improved. Contents of the invention [0003] In view of this, the present invention proposes a multivariate general model platform modeling method, electronic equipment, and computer-readable storage media. By establishing a multivariate general model algorithm library, it can quickly access the modeling business, save costs, and integrate different types of models Algorithms a...

AI Technical Summary

Problems solved by technology

[0002] At present, there is no general solution for business prediction in each scenario. In addition, the high cost of Spark big data learning leads to slow access to modeling tasks for new projects or new businesses and low code reuse rate.

Therefore, the design of the modeling method in the prior art is not reasonable enough and urgently needs to be improved

Images